2_17_09_FeedforwardNetworks_1

2_17_09_FeedforwardNetworks_1 - The simplest neural-network...

Info iconThis preview shows pages 1–12. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: The simplest neural-network model for brain computations is feedforward with one output. The simplest model for the postsynaptic current in a linear feedforward network is dI s dt = I s s + w b u b t ( ) s b = 1 N s dI s dt = I s + w u We assume a steady-state current-to- action-potential-frequency function (the activation function), F(I s ). An extreme model uses very fast firing: For very slow firing: s dI s dt = I s + w u with v = F I s ( ) r dv dt = v + F I s t ( ) ( ) r dv dt = v + F w u ( ) Neurons can display both slow- and fast-firing properties as the mean input current varies. The simplest neural-network model for brain computations is feedforward with one output. A full feedforward network has vector inputs and outputs connected by a weight matrix. For a feedforward network: r dv a dt = v a + F W ab b = 1 N a u b r d v dt = v + F W u ( ) Reaching with hands is independent of gaze; how does the brain transform coordinates? Premotor cortex neurons encode the site of objects in body-based, not retinal, coordinates. objects in body-based, not retinal, coordinates....
View Full Document

This note was uploaded on 06/08/2009 for the course BME 575L taught by Professor Grzywacz during the Spring '09 term at USC.

Page1 / 21

2_17_09_FeedforwardNetworks_1 - The simplest neural-network...

This preview shows document pages 1 - 12. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online